© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 41214
    Prev
    Next
    INDEX
    Explanations

    social

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     folks
    -0.26
    ozilla
    -0.26
    //===
    -0.26
     (?
    -0.25
    ç»Ļ大家
    -0.24
     bites
    -0.24
    åĸī
    -0.24
    sembles
    -0.24
     Ont
    -0.24
    @show
    -0.23
    POSITIVE LOGITS
    å±
    0.26
    abras
    0.26
    odash
    0.26
    Attr
    0.25
    åĨį
    0.25
    æľ¬è´¨ä¸Ĭ
    0.24
    å±ıéļľ
    0.24
     bó
    0.24
    avior
    0.24
    inheritDoc
    0.24
    Activations Density 0.304%

    No Known Activations